© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18527
    Prev
    Next
    INDEX
    Explanations

    http and https links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     -
    0.51
     perplexing
    0.50
    𝐀
    0.47
    ):
    0.46
     BLACK
    0.44
    𝑨
    0.44
    Find
    0.44
     واحدة
    0.43
     *:
    0.43
    𝗕
    0.43
    POSITIVE LOGITS
     foll
    0.57
    сии
    0.55
    лли
    0.54
     edilir
    0.52
    arının
    0.52
     değiştir
    0.52
    ovíd
    0.52
     nieve
    0.51
    στε
    0.51
    ly
    0.50
    Activations Density 0.002%

    No Known Activations